Voice processing method and device

The invention relates to the field of computer technologies, and provides a voice processing method and device. The voice processing method comprises the steps of parsing an acquired voice instructionto obtain voice feature information corresponding to the voice instruction; detecting semantic features contained in the voice feature information according to a preset semantic recognition model toobtain a detection result, wherein the detection result contains a semantic recognition result with the highest semantic matching degree; and performing corresponding processing based on the detectionresult containing the semantic recognition result. According to the invention, voice-based processing is realized, the processing process of realizing a corresponding operation without manual operations is achieved through the control of the voice instruction, and the manual labor is reduced. Meanwhile, effective processing for a complex voice instruction is realized, the processing range is expanded, the using experience